google-research / sputnik
A library of GPU kernels for sparse matrix operations.
☆260Updated 4 years ago
Alternatives and similar repositories for sputnik:
Users that are interested in sputnik are comparing it to the libraries listed below
- ☆190Updated 8 months ago
- Assembler for NVIDIA Volta and Turing GPUs☆214Updated 3 years ago
- CUDA Matrix Multiplication Optimization☆173Updated 8 months ago
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆135Updated last year
- ☆91Updated 11 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆327Updated 6 months ago
- An extension library of WMMA API (Tensor Core API)☆91Updated 8 months ago
- Training neural networks in TensorFlow 2.0 with 5x less memory☆130Updated 3 years ago
- Step-by-step optimization of CUDA SGEMM☆293Updated 2 years ago
- Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.☆329Updated 2 months ago
- ☆55Updated 2 months ago
- Shared Middle-Layer for Triton Compilation☆232Updated last week
- ☆49Updated last year
- ☆162Updated 9 months ago
- ☆141Updated last month
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆100Updated 8 months ago
- A simple high performance CUDA GEMM implementation.☆352Updated last year
- ☆73Updated 4 months ago
- Research and development for optimizing transformers☆125Updated 4 years ago
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆367Updated 6 months ago
- Code for paper "Design Principles for Sparse Matrix Multiplication on the GPU" accepted to Euro-Par 2018☆73Updated 4 years ago
- MatMul Performance Benchmarks for a Single CPU Core comparing both hand engineered and codegen kernels.☆128Updated last year
- [MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration☆197Updated 2 years ago
- Experimental projects related to TensorRT☆94Updated this week
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆313Updated this week
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆209Updated 5 months ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆86Updated 2 years ago
- Dissecting NVIDIA GPU Architecture☆90Updated 2 years ago
- ☆87Updated last week
- CUDA templates for tile-sparse matrix multiplication based on CUTLASS.☆50Updated 7 years ago